© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3156
    Prev
    Next
    INDEX
    Explanations

    specific domain text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    奴
    -0.22
    éģı
    -0.19
    çij¢
    -0.19
    /MIT
    -0.19
    -initialized
    -0.18
    çĭŀ
    -0.18
    ORIES
    -0.18
    QRST
    -0.18
    )view
    -0.18
    ULER
    -0.18
    POSITIVE LOGITS
    Į¨
    0.24
    ThanOrEqualTo
    0.21
    \Bridge
    0.21
     @{$
    0.20
    '],$_
    0.20
    interopRequire
    0.20
    é¹ŀ
    0.19
    _excerpt
    0.19
    趸
    0.19
    lève
    0.19
    Activations Density 0.009%

    No Known Activations